I’m testing the significance of a predictor through a t-test, after having made an univariate analysis and run a simple linear regression.
I’ve computed the t statistic as follows: since the number of observations is 100, and I’m now analyzing a model with one predictor only, my t test with 98 degrees of freedom at a significance level of alpha = 0.05 is 1.66.
The simple linear regression gave me these results:
Coefficient = 1.74
Standard error = 0.9
t = 1.94
P>|t| = 0.055
95% Confidence Interval = -0.39 + 3.5.
Looking ad the “t” column, I should conclude for the significance of the predictor. However, a p-value slightly bigger than 0.05 (as well as the confidence interval, limited by extremes of opposite signs) would make me look at this variable as a non significant one.
Could you help me interpret these results?
Thank you
Related Posts with T-TEST interpretation
Dropping variables by number of non-missing valuesWorking with Stata 15 on Mac OS Sierra, I'm attempting to work with Oklahoma voting data (available …
Biprobit postestimation predicted probability table using esttab commandHi, I am using biprobit command and then trying to estimate joint probabilities. However, when I tr…
Dynamic panel model with lagged effects of x on YI have dynamic panel data (countries=27 and t=21) with dependent variable (Y) and the independent va…
Issue with UK census data shape filesHi, I have over 200K items with individual latitude longitude coordinates, most in the UK. Ultimatel…
Median survival not reachedHello fellow statalisters, I would like to ask the community for some help regarding a survival ana…
Subscribe to:
Post Comments (Atom)
0 Response to T-TEST interpretation
Post a Comment